935e02bdc6
Add held-out test set validation and S3 multi-pair expansion
...
Test set (Sep 2023 - Dec 2024): only S9_Filtered passes (PF=1.13),
portfolio PF=0.91 FAIL. S3 expansion to GBP_USD, EUR_USD, GBP_AUD
shows no generalization — GBP_JPY remains the only viable pair.
No strategy is consistently profitable across all 4 validation periods.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com >
2026-02-21 12:41:44 +10:00
8df1bac3a4
Add 2025 forward validation: only S3 survives out of 4 strategies
...
Downloaded 2025 data (Oct 2024-Dec 2025) for GBP_JPY H1, GBP_AUD H1,
GBP_USD M15+H1 via Dukascopy. Ran all 4 Phase 2 passing strategies on
2025 data. Results: S7_Tight PF=0.52 FAIL, S9_Filtered PF=0.74 FAIL,
S3 PF=1.05 PASS (+52p), S8_OB PF=0.84 FAIL. Portfolio PF=0.83 (-373p).
Only S3 (Key Level Breakout) maintained edge into 2025.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com >
2026-02-21 12:00:22 +10:00
dce54845c2
Phase 1: Event-driven backtester, 5 strategies, and baseline results
...
- Built event-driven backtesting engine with spread/slippage modeling,
3-TP partial closes, trailing stops, and rich trade logging (20+ features)
- Implemented 5 strategy signal generators (MA Breakout, VWAP Reversal,
Key Level Breakout, EMA Ribbon Scalp, Momentum Exhaustion)
- Full indicator library (EMA, SMA, RSI, ATR, MACD, ADX, Stochastic,
Session VWAP bands, swing points, key levels, RSI divergence)
- Data pipeline: Dukascopy download, validation, 70/30 train/test split
- Baseline results: all 5 strategies generate 200+ trades on training data
(Jan 2021 - Aug 2023), best profit factors 0.82-0.96 on select pairs
- Trade logs and reports saved for Phase 3 ML feature engineering
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com >
2026-02-18 06:04:40 +10:00
Brent Neale